Automated system for customer support

BACKGROUND OF THE INVENTION

0001The present invention relates generally to the field of data processing, and more particularly to an automated customer support system.

0002A customer support system is a source of technical support for an end user of hardware or software. A help desk of a customer support system has traditionally been staffed by a customer service team who interacts with end users contacting the help desk after experiencing some sort of IT issue. The customer service team handles incoming incidents and service requests by documenting the end user's IT issue and opening an IT support ticket.

0003A new comprehensive customer support system has replaced this antiquated operational model. The new comprehensive customer support system streamlines the customer service process by automating the help desk's ticketing process using IT ticketing software. IT ticketing software orchestrates the streamlined, automated workflows, enabling much faster and hassle-free resolution of incidents and service requests logged as IT support tickets. Each IT support ticket documents all of the relevant information pertaining to the incident that needs to be resolved or the service that is requested of the customer service team. IT ticketing software leverages multiple channels to collect and log IT support tickets, including emails, phone calls, self-service portals, mobile applications, live chats, chatbots, and integration with third-party applications. IT ticketing software routes the IT support tickets throughout their life cycle depending on the predefined workflows and automations to which they are subjected.

0004In order to provide the streamlined, automated workflows and resolutions of incidents and service requests, IT ticketing software leverages artificial intelligence (AI) and natural language processing (NLP).

0005A branch of AI known as planning automates reasoning about plans, most importantly the reasoning that goes into formulating a plan to achieve a given goal in a given situation. AI planning is model based. That means the AI planning system takes as an input a description of the initial situation, the actions available to change it, and computes a plan composed of those actions to accomplish the goal when executed.

0006NLP yields insights into the problems driving IT support tickets that might otherwise go unnoticed and unaddressed. NLP yields insights from the unstructured text in the IT support tickets. NLP algorithms go through the unstructured text and “cluster” issues based on the unstructured text specified in the IT support ticket. NLP algorithms include ways to remove “stop words” such as “the”, “a”, and “an” in unstructured text fields. NLP algorithms cluster details about IT support tickets by two-word pairs that are included in a large volumes of uncategorized IT support tickets. An example of a two-word pair may be “account lockout” or “access denied.” On the other hand, if the system includes incident data from log files, an example of a two-word pair may be “incorrect format” or “command failed.”

SUMMARY

0007Aspects of an embodiment of the present invention disclose a method, computer program product, and computer system for building an automated customer support system. A processor receives a set of sentences extracted from a natural language conversation occurring between an IT support system and a user. A processor extracts an initial state and a goal state from the set of sentences using a Natural Language Classifier. A processor extracts one or more actions from the set of sentences. A processor creates a formal planning model incorporating the initial state, the goal state, and one or more formal actions. A processor determines the one or more formal actions are not complete using a first machine learning model. A processor completes the one or more formal actions with one or more missing parts. A processor produces an executable plan using a planner. A processor implements one or more executable scripts according to a sequence of the one or more formal actions of the executable plan using a plan executor.

0008In some aspects of an embodiment of the present invention, a processor runs a seq2seq model that translates the sentence identified as the initial state and the sentence identified as the goal state into a logical expression. A processor adds a corresponding logical expression to the sentence identified as the initial state and a corresponding logical expression to the sentence identified as the goal state.

0009In some aspects of an embodiment of the present invention, a processor extracts a name of each of the one or more actions from the set of sentences. A processor extracts a reason for taking each of the one or more actions from the set of sentences. A processor runs a semantic parser on the set of sentences to detect state transitions when the one or more actions from the set of sentences are applied. A processor extracts one or more pre-conditions and one or more effects of the one or more actions from the set of sentences. A processor converts the one or more actions from the set of sentences written in natural language into one or more formal actions written in planning domain description language.

0010In some aspects of an embodiment of the present invention, a processor produces the one or more missing parts of the one or more formal actions using the second machine learning model.

0011In some aspects of an embodiment of the present invention, a processor requests feedback from the user regarding the one or more formal actions with the one or more missing parts. A processor enables the user to review the one or more formal actions with the one or more missing parts. A processor enables the user to revise the one or more formal actions with the one or more missing parts manually through an iterative dialog system. A processor updates the formal planning model with the one or more missing parts. A processor updates a database with the one or more missing parts.

0012In some aspects of an embodiment of the present invention, the executable plan is the sequence of the one or more formal actions instructing the user how to achieve the goal state.

0013In some aspects of an embodiment of the present invention, a processor maps the one or more formal actions of the executable plan to the one or more executable scripts until all of the one or more formal actions of the executable plan have a corresponding executable script. A processor produces the executable plan by linking together the one or more formal actions in such a way that will satisfy the goal.

0014In some aspects of an embodiment of the present invention, a processor selects the one or more formal actions of the executable plan with a missing executable script. A processor enables the user to provide the missing executable script. A processor updates the database with the missing executable script provided by the user.

BRIEF DESCRIPTION OF THE DRAWINGS

<figref idref="DRAWINGS">FIG. <b>1</b></figref> is a functional block diagram illustrating a distributed data processing environment, in accordance with an embodiment of the present invention;

<figref idref="DRAWINGS">FIG. <b>2</b></figref> is a flowchart illustrating the operational steps of an automated customer support program, on a server within the distributed data processing environment of <figref idref="DRAWINGS">FIG. <b>1</b></figref>, in accordance with an embodiment of the present invention; and

<figref idref="DRAWINGS">FIG. <b>3</b></figref> is a block diagram illustrating the components of a computing device in the distributed data processing environment of <figref idref="DRAWINGS">FIG. <b>1</b></figref>, in accordance with an embodiment of the present invention.

DETAILED DESCRIPTION

0018Embodiments of the present invention recognize that the customer support system has streamlined the customer service process by automating the help desk's ticketing process using IT ticketing software. Embodiments of the present invention recognize that IT ticketing software leverages AI and NLP in order to provide automated workflows and resolutions of incidents and service requests logged as IT support tickets. Embodiments of the present invention recognize that each IT support ticket documents all of the relevant information pertaining to the issue that needs to be resolved or the service that is required to be completed by the customer service team. Embodiments of the present invention recognize that the IT ticketing software leverages multiple channels to collect and log IT support tickets, including emails, phone calls, self-service portals, mobile applications, live chats, chatbots, and integration with third-party applications. Embodiments of the present invention recognize that the IT ticketing software routes the IT support tickets throughout their life cycle depending on the predefined workflows and automations to which they are subjected. Thus, embodiments of the present invention recognize the need to find a way to extract symbolic knowledge (i.e., Planning Domain Description Language (PDDL)) from an IT support ticket.

0019Embodiments of the present invention provide a system and method to extract an initial state, a goal state, and one or more actions from a set of sentences received from a natural language conversation occurring between an IT support system and a user through the one or more channels used to log IT support tickets.

0020Embodiments of the present invention provide a system and method to create a formal planning model with one or more formal actions written in PDDL text. PDDL is a formal knowledge representation language designed to express planning tasks. Developed as a means of facilitating system comparison, PDDL has become a de-facto standard input language of many planning systems. The components of a PDDL planning task include objects (i.e., things in the world that interest us), predicates (i.e., facts that we are interested in, e.g., properties of objects, which can be true or false), an initial state (i.e., the state of the world we start in, i.e., things that are true at the start), a goal state (i.e., the state of the world we want to be true at the end), and actions (i.e., the way of changing the state of the world, i.e., things that happen that change the facts). The planning tasks specified in PDDL are separated into two files: (1) a domain file, which contains predicates and actions, and (2) a problem file, which contains objects, the initial state, and the goal state.

0021Embodiments of the present invention provide a system and method to complete the one or more formal actions that are incomplete and updates the formal planning model. Embodiments of the present invention provide a system and method to produce and implement an executable plan.

0022Embodiments of the present invention provide a system and method to produce an executable plan to achieve the desired goal (i.e., the goal state) by linking together one or more formal actions, while inferring some actions which may not be mentioned explicitly in the text. Embodiments of the present invention provide a system and method to correct and update certain actions of the plan. Embodiments of the present invention provide a system and method to apply the executable plan to the IT support system.

0023Implementation of embodiments of the present invention may take a variety of forms, and exemplary implementation details are discussed subsequently with reference to the Figures.

0024<figref idref="DRAWINGS">FIG. <b>1</b></figref> is a functional block diagram illustrating a distributed data processing environment, generally designated <b>100</b>, in accordance with an embodiment of the present invention. In the depicted embodiment, distributed data processing environment <b>100</b> includes server <b>120</b> and user computing device <b>130</b>, interconnected over network <b>110</b>. Distributed data processing environment <b>100</b> may include additional servers, computers, computing devices, IoT sensors, and other devices not shown. The term “distributed” as used herein describes a computer system that includes multiple, physically distinct devices that operate together as a single computer system. <figref idref="DRAWINGS">FIG. <b>1</b></figref> provides only an illustration of one embodiment of the present invention and does not imply any limitations with regard to the environments in which different embodiments may be implemented. Many modifications to the depicted environment may be made by those skilled in the art without departing from the scope of the invention as recited by the claims.

0025Network <b>110</b> operates as a computing network that can be, for example, a telecommunications network, a local area network (LAN), a wide area network (WAN), such as the Internet, or a combination of the three, and can include wired, wireless, or fiber optic connections. Network <b>110</b> can include one or more wired and/or wireless networks capable of receiving and transmitting data, voice, and/or video signals, including multimedia signals that include voice, data, and video information. In general, network <b>110</b> can be any combination of connections and protocols that will support communications between server <b>120</b>, user computing device <b>130</b>, and other computing devices (not shown) within distributed data processing environment <b>100</b>.

0026Server <b>120</b> operates to run automated customer support program <b>122</b> and to send and/or store data in database <b>124</b>. In an embodiment, server <b>120</b> can send data from database <b>124</b> to user computing device <b>130</b>. In an embodiment, server <b>120</b> can receive data in database <b>124</b> from user computing device <b>130</b>. In an embodiment, server <b>120</b> can be a standalone computing device, a management server, a web server, a mobile computing device, or any other electronic device or computing system capable of receiving, sending, and processing data and capable of communicating with user computing device <b>130</b> via network <b>110</b>. In one or more embodiments, server <b>120</b> can be a computing system utilizing clustered computers and components (e.g., database server computers, application server computers, etc.) that act as a single pool of seamless resources when accessed within distributed data processing environment <b>100</b>, such as in a cloud computing environment. In one or more embodiments, server <b>120</b> can be a laptop computer, a tablet computer, a netbook computer, a personal computer, a desktop computer, a personal digital assistant, a smart phone, or any programmable electronic device capable of communicating with user computing device <b>130</b> and other computing devices (not shown) within distributed data processing environment <b>100</b> via network <b>110</b>. Server <b>120</b> may include internal and external hardware components, as depicted and described in further detail in <figref idref="DRAWINGS">FIG. <b>3</b></figref>.

0027Automated customer support program <b>122</b> operates to extract an initial state, a goal state, and one or more actions from a set of sentences received from a natural language conversation occurring between an IT support system and a user through the one or more channels used to log IT support tickets. Automated customer support program <b>122</b> operates to create a formal planning model. Automated customer support program <b>122</b> operates to complete the one or more formal actions that are incomplete and updates the formal planning model. Automated customer support program <b>122</b> operates to produce and implement an executable plan.

0028In the depicted embodiment, automated customer support program <b>122</b> is a standalone program. In another embodiment, automated customer support program <b>122</b> may be integrated into another software product, such as an IT support software package. In the depicted embodiment, automated customer support program <b>122</b> resides on server <b>120</b>. In another embodiment, automated customer support program <b>122</b> may reside on user computing device <b>130</b> or on another computing device (not shown), provided that automated customer support program <b>122</b> has access to network <b>110</b>. The operational steps of automated customer support program <b>122</b> are depicted and described in further detail with respect to <figref idref="DRAWINGS">FIG. <b>2</b></figref>.

0029Database <b>124</b> operates as a repository for data received, used, and/or generated by automated customer support program <b>122</b>. A database is an organized collection of data. Data includes, but is not limited to, information about user preferences (e.g., general user system settings for user computing device <b>130</b>); information about alert notification preferences; one or more formal actions; executable scripts; executable plans; and any other data received, used, and/or generated by automated customer support program <b>122</b>. Database <b>124</b> can be implemented with any type of device capable of storing data and configuration files that can be accessed and utilized by server <b>120</b>, such as a hard disk drive, a database server, or a flash memory. In an embodiment, database <b>124</b> is accessed by automated customer support program <b>122</b> to store and/or to access the data. In the depicted embodiment, database <b>124</b> resides on server <b>120</b>. In another embodiment, database <b>124</b> may reside on another computing device, server, cloud server, or spread across multiple devices elsewhere (not shown) within distributed data processing environment <b>100</b>, provided that automated customer support program <b>122</b> has access to database <b>124</b>.

0030A user preference is a setting that can be customized for a particular user. A set of default user preferences are assigned to each user of automated customer support program <b>122</b>. A user preference editor can be used to update values to change the default user preferences. User preferences that can be customized include, but are not limited to, general user system settings, alert notification settings, and machine-learned data collection and storage settings. Machine-learned data includes, but is not limited to, data regarding past results of iterations of automated customer support program <b>122</b> and a user's previous response to an alert notification sent by automated customer support program <b>122</b>. Machine-learned data comes from automated customer support program <b>122</b> self-learning how to automatically extract the initial state, the goal state, and the problem domain from a set of sentences received from a natural language conversation occurring between the IT support system and a user through the one or more channels used to log IT support tickets; self-learning how to create a formal planning model; self-learning how to complete the one or more formal actions that are incomplete and update the formal planning model; and self-learning how to produce and implement an executable plan. Automated customer support program <b>122</b> self-learns by tracking user activity and improves with each iteration of automated customer support program <b>122</b>.

0031User computing device <b>130</b> operates to run user interface <b>132</b> through which a user can interact with automated customer support program <b>122</b> on server <b>120</b>. In an embodiment, user computing device <b>130</b> is a device that performs programmable instructions. For example, user computing device <b>130</b> may be an electronic device, such as a laptop computer, a tablet computer, a netbook computer, a personal computer, a desktop computer, a smart phone, or any programmable electronic device capable of running user interface <b>132</b> and of communicating (i.e., sending and receiving data) with automated customer support program <b>122</b> via network <b>110</b>. In general, user computing device <b>130</b> represents any programmable electronic device or a combination of programmable electronic devices capable of executing machine readable program instructions and communicating with other computing devices (not shown) within distributed data processing environment <b>100</b> via network <b>110</b>. In the depicted embodiment, user computing device <b>130</b> includes an instance of user interface <b>132</b>. User computing device <b>130</b> may include components as described in further detail in <figref idref="DRAWINGS">FIG. <b>3</b></figref>.

0032User interface <b>132</b> operates as a local user interface between automated customer support program <b>122</b> on server <b>120</b> and a user of user computing device <b>130</b>. In some embodiments, user interface <b>132</b> is a graphical user interface (GUI), a web user interface (WUI), and/or a voice user interface (VUI) that can display (i.e., visually) or present (i.e., audibly) text, documents, web browser windows, user options, application interfaces, and instructions for operations sent from automated customer support program <b>122</b> to a user via network <b>110</b>. User interface <b>132</b> can also display or present alerts including information (such as graphics, text, and/or sound) sent from automated customer support program <b>122</b> to a user via network <b>110</b>. In an embodiment, user interface <b>132</b> is capable of sending and receiving data (i.e., to and from automated customer support program <b>122</b> via network <b>110</b>, respectively). Through user interface <b>132</b>, a user can set user preferences and alert notification preferences.

0033<figref idref="DRAWINGS">FIG. <b>2</b></figref> is a flowchart, generally designated <b>200</b>, illustrating the operational steps of automated customer support program <b>122</b> on server <b>120</b> in distributed data processing environment <b>100</b> of <figref idref="DRAWINGS">FIG. <b>1</b></figref>, in accordance with an embodiment of the present invention. In an embodiment, automated customer support program <b>122</b> operates to extract an initial state, a goal state, and one or more actions from a set of sentences received from a natural language conversation occurring between an IT support system and a user through the one or more channels used to log IT support tickets. In an embodiment, automated customer support program <b>122</b> creates a formal planning model. In an embodiment, automated customer support program <b>122</b> completes the one or more formal actions that are incomplete and updates the formal planning model. In an embodiment, automated customer support program <b>122</b> produces and implements an executable plan. It should be appreciated that the process depicted in <figref idref="DRAWINGS">FIG. <b>2</b></figref> illustrates one possible iteration of automated customer support program <b>122</b>, which may be repeated after a conversation between an IT support system and a user is logged by automated customer support program <b>122</b>.

0034In step <b>210</b>, automated customer support program <b>122</b> receives a set of sentences. In an embodiment, automated customer support program <b>122</b> receives a set of sentences extracted from a natural language conversation occurring between an IT support system and a user through one or more channels used to log IT support tickets. The one or more channels used to log IT support tickets includes, but is not limited to, emails, phone calls, self-service portals, mobile applications, live chats, chatbots, and integration with third-party applications. In an embodiment, automated customer support program <b>122</b> receives a set of sentences in natural language format. In an embodiment, automated customer support program <b>122</b> receives a set of sentences describing an initial state and a goal state. The initial state describes the state from where automated customer support program <b>122</b> starts, i.e., the state of the IT issue when logged in the IT support ticket. The goal state describes the state where automated customer support program <b>122</b> wants to end, i.e., the state after the IT issue is solved and the IT support ticket is closed. In an embodiment, automated customer support program <b>122</b> receives a set of sentences describing a problem domain. The problem domain is a formal description of the planning actions corresponding to the steps allowed in the domain with their preconditions and effects, i.e., the one or more actions required to be executed to achieve the goal state, i.e., the one or more actions required to be executed to solve the IT issue and to close the IT support ticket. The problem domain will hereinafter be referred to as “the one or more actions”.

0035For example, automated customer support program <b>122</b> receives a set of sentences extracted from a natural language conversation occurring between the IT support system and a user through a chatbot, a channel used to log IT support tickets. The user's issue, i.e., the index IDX<b>1</b> in partition P<b>1</b> in database DB<b>2</b>_D<b>1</b> is broken and needs to be rebuilt, is described in the set of sentences. The steps required to be executed to resolve the user's issue is also described in the set of sentences: “Step 1 is to login to the database using administrative credentials. Step 2 is to join tables T<b>2</b> and T<b>4</b> together on fields T<b>2</b>.fieldA and T<b>4</b>.fieldC. Step 4 is to create index IDX<b>1</b> on fieldD of the previous join. Step 5 is to run the maintenance SQL procedure maintain( ) before creating index IDX<b>1</b>. Step 6 is to logout.” The problem is that Step 3 (to delete the previous index IDX<b>1</b>) is not explicitly mentioned.

0036In step <b>220</b>, automated customer support program <b>122</b> extracts an initial state and a goal state from the set of sentences. In an embodiment, responsive to receiving a set of sentences, automated customer support program <b>122</b> extracts an initial state and a goal state from the set of sentences. In an embodiment, customer support program <b>122</b> extracts an initial state and a goal state from the set of sentences using a Natural Language Classifier (NLC). The NLC is trained on labeled examples of the initial state and the goal state. The NLC allows a user to classify text into custom categories, at scale. The NLC utilizes an ensemble of classification models, along with unsupervised and supervised learning techniques, to achieve high accuracy levels. After the training data is assembled, the NLC evaluates the data against multiple support vector machines and a convolutional neural network using deep learning. Continuing the above example, automated customer support program <b>122</b> identifies the initial state to be a broken index, IDX<b>1</b>, in partition P<b>1</b> in database DB<b>2</b>_D<b>1</b> and identifies the goal state to be a properly functioning index.

0037In an embodiment, automated customer support program <b>122</b> runs a seq2seq model. In an embodiment, automated customer support program <b>122</b> runs a seq2seq model on the sentence identified as the initial state and on the sentence identified as the goal state. The seq2seq model translates the sentence identified as the initial state and the sentence identified as the goal state into a logical expression. A logical expression is grounded with one or more objects, i.e., the named entities extracted from the sentence. In an embodiment, automated customer support program <b>122</b> adds a corresponding logical expression to the sentence identified as the initial state and to the sentence identified as the goal state, e.g., IS if the sentence is an initial state or GS if the sentence is a goal state.

0038In step <b>230</b>, automated customer support program <b>122</b> extracts the one or more actions from the set of sentences. In an embodiment, responsive to identifying the initial state and the goal state from the set of sentences, automated customer support program <b>122</b> extracts the one or more actions from the set of sentences. In an embodiment, automated customer support program <b>122</b> extracts a name of each of the one or more actions from the set of sentences. In an embodiment, automated customer support program <b>122</b> extracts a reason for taking the one or more actions from the set of sentences. Continuing the above example, automated customer support program <b>122</b> extracts the one or more actions from the set of sentences. The one or more actions include logging in to the database using administrative credentials, joining tables T<b>2</b> and T<b>4</b> together on fields T<b>2</b>.fieldA and T<b>4</b>.fieldC, creating index IDX<b>1</b> on fieldD of the previous join, running the maintenance SQL procedure maintain( )before creating index IDX<b>1</b>, and logging out.

0039In an embodiment, automated customer support program <b>122</b> runs a semantic parser (e.g., verbnet) on the set of sentences. In an embodiment, automated customer support program <b>122</b> runs a semantic parser on the set of sentences to detect state transitions when the one or more actions are applied. In an embodiment, automated customer support program <b>122</b> extracts the pre-conditions and effects of the one or more actions from the set of sentences. In one or more embodiments, automated customer support program <b>122</b> sets the pre-conditions and effects of the one or more actions based on the state transitions detected. Continuing the above example, automated customer support program <b>122</b> identifies a pre-condition to the first action to be executed to fix the problem, i.e., logging into the database. The pre-condition identified is to obtain administrative credentials.

0040In an embodiment, automated customer support program <b>122</b> adopts a PDDL form of representation of the set of sentences. In an embodiment, automated customer support program <b>122</b> formalizes the set of sentences by converting the one or more actions from the set of sentences into one or more formal actions written in PDDL text. In an embodiment, automated customer support program <b>122</b> incorporates the name of the one or more actions, the reason for taking the one or more actions into the one or more formal actions, and the pre-conditions and effects of the one or more actions. In an embodiment, automated customer support program <b>122</b> creates a formal planning model. In an embodiment, automated customer support program <b>122</b> creates a formal planning model with the initial state, the goal state, and the one or more formal actions.

0041In decision <b>240</b>, automated customer support program <b>122</b> determines whether each of the one or more formal actions included in the formal planning model is complete. In an embodiment, responsive to extracting the one or more actions from the set of sentences, automated customer support program <b>122</b> determines whether each of the one or more formal actions included in the formal planning model is complete. In an embodiment, automated customer support program <b>122</b> determines whether each of the one or more formal actions included in the formal planning model is complete using a machine learning model. The machine learning model is trained on a dataset containing examples of complete and incomplete formal actions and can predict whether each of the one or more formal actions is complete or incomplete.

0042If automated customer support program <b>122</b> determines that each of the one or more formal actions included in the formal planning model are complete (decision <b>240</b>, YES branch), then automated customer support program <b>122</b> produces an executable plan (step <b>260</b>). If automated customer support program <b>122</b> determines that each of the one or more formal actions included in the formal planning model are not complete (decision <b>240</b>, NO branch), then automated customer support program <b>122</b> completes the one or more formal incomplete actions (step <b>250</b>).

0043For example, automated customer support program <b>122</b> determines the process of mapping text to action descriptions is not complete because the actions are not complete. Automated customer support program <b>122</b> must complete the formal actions by comparing or leveraging a database of previously extracted actions which are corrected or are assumed to be correct. Automated customer support program <b>122</b> must complete the formal actions by training a new model that predicts how to complete an action description.

0044In step <b>250</b>, automated customer support program <b>122</b> completes the one or more formal actions that are incomplete. In an embodiment, responsive to determining that each of the one or more formal actions are not complete, then automated customer support program <b>122</b> completes the one or more formal actions that are incomplete. In an embodiment, automated customer support program <b>122</b> completes the one or more formal actions that are incomplete based on the initial state and the goal state. In an embodiment, automated customer support program <b>122</b> completes the one or more formal actions that are incomplete using a machine learning model. The machine learning model is trained on a dataset containing complete and incomplete formal actions using an encoder-decoder deep learning model and can predict the one or more missing parts of the one or more formal actions that are incomplete. The machine learning model leverages existing formal actions stored in a database, e.g., database <b>124</b>. In an embodiment, automated customer support program <b>122</b> completes the one or more formal actions that are incomplete with an existing formal action from a database, e.g., database <b>124</b>.

0045In an embodiment, automated customer support program <b>122</b> requests feedback from the user. In an embodiment, automated customer support program <b>122</b> requests feedback from the user through user interface <b>132</b> of user computing device <b>130</b>. In an embodiment, automated customer support program <b>122</b> requests feedback regarding the one or more formal actions that were completed. In an embodiment, automated customer support program <b>122</b> requests feedback in order to automatically correct the one or more formal actions that are not complete. In an embodiment, automated customer support program <b>122</b> enables a user to review the one or more formal actions that are not complete. In an embodiment, automated customer support program <b>122</b> enables a user to revise the one or more formal actions that are not complete manually through an iterative dialog system. In an embodiment, automated customer support program <b>122</b> enables a user to interact with the iterative dialog system through user interface <b>132</b> of user computing device <b>130</b>. For example, automated customer support program <b>122</b> presents a formal action to a user and requests feedback from the user on whether the formal action is complete or incomplete. Subsequently, the user can label the action as complete or incomplete. If the action is incomplete, the user can label the action as incomplete and provide a reason why the action is incomplete, e.g., the action is missing a pre-condition or the action produces the wrong effect. In addition, the user can provide the complete action.

0046In an embodiment, automated customer support program <b>122</b> uses the feedback to learn to automatically identify an incomplete action and subsequently to generate the correct complete action. In an embodiment, automated customer support program <b>122</b> uses the feedback to improve automated customer support program <b>122</b> in producing an executable plan. In an embodiment, automated customer support program <b>122</b> uses the feedback to improve automated customer support program <b>122</b> in producing an executable plan using a recommendation system. Recommendation systems include, but are not limited to, reinforcement learning, machine learning, collaborative filtering, matrix decomposition, clustering, and/or any deep learning approach.

0047In an embodiment, automated customer support program <b>122</b> produces one or more completed formal actions. In an embodiment, automated customer support program <b>122</b> updates the formal planning model with the one or more completed formal actions. In an embodiment, automated customer support program <b>122</b> updates the database, e.g., database <b>124</b>, with the one or more completed formal actions.

0048In step <b>260</b>, automated customer support program <b>122</b> produces an executable plan. In an embodiment, responsive to completing the one or more formal actions that are incomplete, automated customer support program <b>122</b> produces an executable plan. In an embodiment, automated customer support program <b>122</b> produces an executable plan using a planner. The planner is an algorithm that, when given an initial state, a goal state, and a set of actions, computes an executable plan. The executable plan is a sequence of one or more formal actions instructing the user how to achieve the goal state. In an embodiment, automated customer support program <b>122</b> produces an executable plan. In an embodiment, automated customer support program <b>122</b> produces an executable plan by linking together the one or more formal actions in such a way that will achieve the goal state. Continuing the above example, automated customer support program <b>122</b> produces an executable plan to fix the index IDX<b>1</b> in partition P<b>1</b> of the user's database DB<b>2</b>_D<b>1</b>. The executable plan involves the steps to rebuild the index.

0049In an embodiment, automated customer support program <b>122</b> maps the one or more formal actions of the executable plan. In an embodiment, automated customer support program <b>122</b> maps the one or more formal actions of the executable plan to executable scripts. The executable script is a code that can be executed on a user computing device. In an embodiment, automated customer support program <b>122</b> maps the one or more formal actions of the executable plan until all of the one or more formal actions of the executable plan have a corresponding script. In an embodiment, automated customer support program <b>122</b> selects the one or more formal actions of the executable plan with a missing executable script. In an embodiment, automated customer support program <b>122</b> enables the user to provide the missing executable scripts. In an embodiment, automated customer support program <b>122</b> adds the missing executable scripts to a database, e.g., database <b>124</b>.

0050In step <b>270</b>, automated customer support program <b>122</b> implements the executable plan. In an embodiment, responsive to automated customer support program <b>122</b> producing an executable plan, automated customer support program <b>122</b> implements the executable plan. In an embodiment, automated customer support program <b>122</b> implements the executable plan using a plan executor. In an embodiment, automated customer support program <b>122</b> implements the executable plan by executing the scripts. In an embodiment, automated customer support program <b>122</b> executes the scripts according to the sequences of actions in the executable plan. In an embodiment, automated customer support program <b>122</b> executes the scripts on user computing device <b>130</b>. In another embodiment, automated customer support program <b>122</b> enables the user to implement the executable plan. In an embodiment, automated customer support program <b>122</b> enables the user to implement the executable plan manually on user computing device <b>130</b>. In an embodiment, automated customer support program <b>122</b> outputs the executable plan to the user as an alert notification. In an embodiment, automated customer support program <b>122</b> outputs the executable plan to the user as an alert notification through user interface <b>132</b> of user computing device <b>130</b>. In an embodiment, automated customer support program <b>122</b> stores the executable plan. In an embodiment, automated customer support program <b>122</b> stores the executable plan in a database, e.g., database <b>124</b>.

0051<figref idref="DRAWINGS">FIG. <b>3</b></figref> is a block diagram illustrating the components of computer system <b>300</b>, suitable for server <b>120</b> and/or user computing device <b>130</b> within distributed data processing environment <b>100</b> of <figref idref="DRAWINGS">FIG. <b>1</b></figref>, in accordance with an embodiment of the present invention. It should be appreciated that <figref idref="DRAWINGS">FIG. <b>3</b></figref> provides only an illustration of one implementation and does not imply any limitations with regard to the environments in which different embodiments can be implemented. Many modifications to the depicted environment can be made.

0052Computer system <b>300</b> includes processor(s) <b>304</b>, memory <b>306</b>, cache <b>316</b>, communications fabric <b>302</b>, persistent storage <b>308</b>, input/output (I/O) interface(s) <b>312</b>, and communications unit <b>310</b>.

0053Communications fabric <b>302</b> provides communications between memory <b>306</b>, cache <b>316</b>, persistent storage <b>308</b>, input/output (I/O) interface(s) <b>312</b>, and communications unit <b>310</b>. Communications fabric <b>302</b> can be implemented with any architecture designed for passing data and/or control information between processors (such as microprocessors, communications and network processors, etc.), system memory, peripheral devices, and any other hardware components within a system. For example, communications fabric <b>302</b> can be implemented with one or more buses or a cross switch.

0054Memory <b>306</b> and persistent storage <b>308</b> are computer readable storage media. In this embodiment, memory <b>306</b> includes random access memory (RAM). In general, memory <b>306</b> can include any suitable volatile or non-volatile computer readable storage media. Cache <b>316</b> is a fast memory that enhances the performance of computer processor(s) <b>304</b> by holding recently accessed data, and data near accessed data, from memory <b>306</b>.

0055Program instructions and data (e.g., software and data <b>314</b>) used to practice embodiments of the present invention may be stored in persistent storage <b>308</b> and in memory <b>306</b> for execution and/or access by one or more of the respective processor(s) <b>304</b> via cache <b>316</b>. In an embodiment, persistent storage <b>308</b> includes a magnetic hard disk drive. Alternatively, or in addition to a magnetic hard disk drive, persistent storage <b>308</b> can include a solid-state hard drive, a semiconductor storage device, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, or any other computer readable storage media that is capable of storing program instructions or digital information.

0056The media used by persistent storage <b>308</b> may also be removable. For example, a removable hard drive may be used for persistent storage <b>308</b>. Other examples include optical and magnetic disks, thumb drives, and smart cards that are inserted into a drive for transfer onto another computer readable storage medium that is also part of persistent storage <b>308</b>. Software and data <b>314</b> can be stored in persistent storage <b>308</b> for access and/or execution by one or more of the respective processor(s) <b>304</b> via cache <b>316</b>. With respect to user computing device <b>130</b>, software and data <b>314</b> includes user interface <b>132</b>. With respect to server <b>120</b>, software and data <b>314</b> includes automated customer support program <b>122</b>.

0057Communications unit <b>310</b>, in these examples, provides for communications with other data processing systems or devices. In these examples, communications unit <b>310</b> includes one or more network interface cards. Communications unit <b>310</b> may provide communications through the use of either or both physical and wireless communications links. Program instructions and data (e.g., software and data <b>314</b>) used to practice embodiments of the present invention may be downloaded to persistent storage <b>308</b> through communications unit <b>310</b>.

0058I/O interface(s) <b>312</b> allows for input and output of data with other devices that may be connected to server <b>120</b> and/or user computing device <b>130</b>. For example, I/O interface(s) <b>312</b> may provide a connection to external device(s) <b>318</b>, such as a keyboard, a keypad, a touch screen, and/or some other suitable input device. External device(s) <b>318</b> can also include portable computer readable storage media, such as, for example, thumb drives, portable optical or magnetic disks, and memory cards. Program instructions and data (e.g., software and data <b>314</b>) used to practice embodiments of the present invention can be stored on such portable computer readable storage media and can be loaded onto persistent storage <b>308</b> via I/O interface(s) <b>312</b>. I/O interface(s) <b>312</b> also connect to display <b>320</b>.

0059Display <b>320</b> provides a mechanism to display data to a user and may be, for example, a computer monitor.

0060The programs described herein are identified based upon the application for which they are implemented in a specific embodiment of the invention. However, it should be appreciated that any particular program nomenclature herein is used merely for convenience, and thus the invention should not be limited to use solely in any specific application identified and/or implied by such nomenclature.

0061The present invention may be a system, a method, and/or a computer program product at any possible technical detail level of integration. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.

0062The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

0063Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.

0064Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.

0065While particular embodiments of the present invention have been shown and described here, it will be understood to those skilled in the art that, based upon the teachings herein, changes and modifications may be made without departing from the embodiments and its broader aspects. Therefore, the appended claims are to encompass within their scope all such changes and modifications as are within the true spirit and scope of the embodiments. Furthermore, it is to be understood that the embodiments are solely defined by the appended claims. It will be understood by those with skill in the art that if a specific number of an introduced claim element is intended, such intent will be explicitly recited in the claim, and in the absence of such recitation no such limitation is present. For a non-limiting example, as an aid to understand, the following appended claims contain usage of the introductory phrases “at least one” and “one or more” to introduce claim elements. However, the use of such phrases should not be construed to imply that the introduction of a claim element by the indefinite articles “a” or “an” limits any particular claim containing such introduced claim element to embodiments containing only one such element, even when the same claim includes the introductory phrases “at least one” or “one or more” and indefinite articles such as “a” or “an”, the same holds true for the use in the claims of definite articles.

0066Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

0067These computer readable program instructions may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart illustrations and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart illustrations and/or block diagram block or blocks.

0068The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart illustrations and/or block diagram block or blocks.

0069The flowchart illustrations and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart illustrations or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each flowchart illustration and/or block of the block diagrams, and combinations of flowchart illustration and/or blocks in the block diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

0070The descriptions of the various embodiments of the present invention have been presented for purposes of illustration but are not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the invention. The terminology used herein was chosen to best explain the principles of the embodiment, the practical application or technical improvement over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.